FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214893216> ?p ?o ?g. }

• W4214893216 endingPage "116748" @default.
• W4214893216 startingPage "116748" @default.
• W4214893216 abstract "Supervisory Control and Data Acquisition (SCADA) systems supervise and monitor critical infrastructures and industrial processes. However, SCADA systems running on conventional network architecture have scalability and manageability limitations. Through its programmable dynamic architecture, Software Defined Network (SDN) technology offers rapid configuration, scalability, and better manageability for SCADA systems. Combining existing SCADA systems with SDN has produced more practical SDN-based SCADA systems. However, due to their sensitive positions, SCADA systems are the targets of highly dangerous cyberattacks. In particular, failure to accurately detect and take action against cyberattacks like Distributed Denial of Service (DDoS) may lead to service disruption in SDN-based SCADA systems which may cause loss of life or massive financial losses. This study suggested the Recurrent Neural Network (RNN) classifier model, including two separate parallel deep learning-based methods, Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), to better the detection of DDoS attacks targeting SDN-based SCADA systems. The proposed parallel structure was trained from end to end with a training dataset and tested with the validation dataset. This model was processed in the transfer learning procedure. The features were extracted with the training dataset, and the extracted features were classified with Support Vector Machines (SVM). While in transfer learning, the validation data was used in feature extraction and obtained features were classified with a trained SVM classifier. As part of the work, a sample dataset containing both DDoS attacks and regular network traffic data was created using an experimentally generated SDN-based SCADA topology. While experimental works yielded an accuracy of 97.62% for DDoS attack detection, transfer learning allowed a performance improvement of around 5%. The results have shown that the proposed RNN deep learning classifier model can effectively detect DDoS attacks targeting SDN-based SCADA systems." @default.
• W4214893216 created "2022-03-05" @default.
• W4214893216 creator A5029891409 @default.
• W4214893216 creator A5042354008 @default.
• W4214893216 creator A5045216943 @default.
• W4214893216 creator A5077647596 @default.
• W4214893216 date "2022-07-01" @default.
• W4214893216 modified "2023-10-03" @default.
• W4214893216 title "A novel approach for accurate detection of the DDoS attacks in SDN-based SCADA systems based on deep recurrent neural networks" @default.
• W4214893216 cites W1973652215 @default.
• W4214893216 cites W2007111180 @default.
• W4214893216 cites W2061243822 @default.
• W4214893216 cites W2067453331 @default.
• W4214893216 cites W2087432251 @default.
• W4214893216 cites W2091236895 @default.
• W4214893216 cites W2518905448 @default.
• W4214893216 cites W2519428799 @default.
• W4214893216 cites W2520381575 @default.
• W4214893216 cites W2727477768 @default.
• W4214893216 cites W2736616122 @default.
• W4214893216 cites W2799843691 @default.
• W4214893216 cites W2800773710 @default.
• W4214893216 cites W2932520042 @default.
• W4214893216 cites W2958780305 @default.
• W4214893216 cites W2963136924 @default.
• W4214893216 cites W2964289795 @default.
• W4214893216 cites W2970413753 @default.
• W4214893216 cites W3001473078 @default.
• W4214893216 cites W3005741980 @default.
• W4214893216 cites W3013930364 @default.
• W4214893216 cites W3015915789 @default.
• W4214893216 cites W3024761859 @default.
• W4214893216 cites W3033513857 @default.
• W4214893216 cites W3034198581 @default.
• W4214893216 cites W3034640547 @default.
• W4214893216 cites W3112778273 @default.
• W4214893216 cites W3120450981 @default.
• W4214893216 doi "https://doi.org/10.1016/j.eswa.2022.116748" @default.
• W4214893216 hasPublicationYear "2022" @default.
• W4214893216 type Work @default.
• W4214893216 citedByCount "19" @default.
• W4214893216 countsByYear W42148932162022 @default.
• W4214893216 countsByYear W42148932162023 @default.
• W4214893216 crossrefType "journal-article" @default.
• W4214893216 hasAuthorship W4214893216A5029891409 @default.
• W4214893216 hasAuthorship W4214893216A5042354008 @default.
• W4214893216 hasAuthorship W4214893216A5045216943 @default.
• W4214893216 hasAuthorship W4214893216A5077647596 @default.
• W4214893216 hasConcept C108583219 @default.
• W4214893216 hasConcept C110875604 @default.
• W4214893216 hasConcept C111919701 @default.
• W4214893216 hasConcept C113863187 @default.
• W4214893216 hasConcept C119599485 @default.
• W4214893216 hasConcept C119857082 @default.
• W4214893216 hasConcept C12267149 @default.
• W4214893216 hasConcept C124101348 @default.
• W4214893216 hasConcept C127413603 @default.
• W4214893216 hasConcept C154945302 @default.
• W4214893216 hasConcept C35525427 @default.
• W4214893216 hasConcept C38822068 @default.
• W4214893216 hasConcept C41008148 @default.
• W4214893216 hasConcept C48044578 @default.
• W4214893216 hasConcept C50644808 @default.
• W4214893216 hasConcept C75684735 @default.
• W4214893216 hasConcept C77088390 @default.
• W4214893216 hasConcept C79403827 @default.
• W4214893216 hasConceptScore W4214893216C108583219 @default.
• W4214893216 hasConceptScore W4214893216C110875604 @default.
• W4214893216 hasConceptScore W4214893216C111919701 @default.
• W4214893216 hasConceptScore W4214893216C113863187 @default.
• W4214893216 hasConceptScore W4214893216C119599485 @default.
• W4214893216 hasConceptScore W4214893216C119857082 @default.
• W4214893216 hasConceptScore W4214893216C12267149 @default.
• W4214893216 hasConceptScore W4214893216C124101348 @default.
• W4214893216 hasConceptScore W4214893216C127413603 @default.
• W4214893216 hasConceptScore W4214893216C154945302 @default.
• W4214893216 hasConceptScore W4214893216C35525427 @default.
• W4214893216 hasConceptScore W4214893216C38822068 @default.
• W4214893216 hasConceptScore W4214893216C41008148 @default.
• W4214893216 hasConceptScore W4214893216C48044578 @default.
• W4214893216 hasConceptScore W4214893216C50644808 @default.
• W4214893216 hasConceptScore W4214893216C75684735 @default.
• W4214893216 hasConceptScore W4214893216C77088390 @default.
• W4214893216 hasConceptScore W4214893216C79403827 @default.
• W4214893216 hasLocation W42148932161 @default.
• W4214893216 hasOpenAccess W4214893216 @default.
• W4214893216 hasPrimaryLocation W42148932161 @default.
• W4214893216 hasRelatedWork W2584408238 @default.
• W4214893216 hasRelatedWork W2803710604 @default.
• W4214893216 hasRelatedWork W3014300295 @default.
• W4214893216 hasRelatedWork W3136979370 @default.
• W4214893216 hasRelatedWork W3189515467 @default.
• W4214893216 hasRelatedWork W4205568523 @default.
• W4214893216 hasRelatedWork W4285106639 @default.
• W4214893216 hasRelatedWork W4285337355 @default.
• W4214893216 hasRelatedWork W4293567684 @default.
• W4214893216 hasRelatedWork W4311106074 @default.
• W4214893216 hasVolume "197" @default.

• next